Calculadora
Calculadora Costo Embeddings AI
Estima costo de embedding único y recurrente entre 9+ providers. Mete tamaño del corpus, estrategia de chunk, frecuencia de refresh.
Precios actualizados:
El AITOT Embeddings Cost calculator estima embedding corpus one-time + re-embed recurring en 9 proveedores — OpenAI text-embedding-3-small/large, Cohere Embed v4, Voyage 3 Lite/standard, Jina v3, BGE-M3 (self-host), Mistral, Google, Azure.
Para corpus 1M documentos a 500 tokens promedio = 500M tokens. OpenAI text-embedding-3-small: $10. OpenAI 3-large: $65. Cohere Embed v4: $50. Mayoría de bills one-time son pequeños; recurring re-embedding es lo que escala.
Toggle refresh frequency (0 = nunca, 0.25 = cada 4 meses, 1 = mensual, 4 = semanal). Sobre 5B tokens/mes, self-hosted BGE-M3 en H100 bate OpenAI.
Más barato · año 1
Together · BGE-M3
1024 dim · 8,192 máx tokens
$2
| Proveedor | Modelo | $ / 1M tokens | Costo embed único | Costo mensual | Año 1 |
|---|---|---|---|---|---|
| Together | BGE-M3 1024 dim · Self-host open weights for $0 | $0.008 | $0.40 | $0.14 | $2 |
| Together | bge-large-en-v1.5 1024 dim | $0.008 | $0.40 | $0.14 | $2 |
| Fireworks | nomic-embed-text-v1.5 768 dim | $0.008 | $0.40 | $0.14 | $2 |
| Jina AI | jina-embeddings-v3 1024 dim · configurable | $0.012 | $0.60 | $0.21 | $3 |
| Jina AI | jina-embeddings-v4 2048 dim · configurable | $0.018 | $0.90 | $0.31 | $5 |
| OpenAI | text-embedding-3-small 1536 dim · configurable | $0.02 | $1.00 | $0.35 | $5 |
| Voyage AI | voyage-4-lite 512 dim · 200M tokens free | $0.02 | $1.00 | $0.35 | $5 |
| Voyage AI | voyage-3-lite 512 dim | $0.02 | $1.00 | $0.35 | $5 |
| Amazon Bedrock | Titan Embed v2 1024 dim · configurable | $0.02 | $1.00 | $0.35 | $5 |
| Voyage AI | voyage-4 1024 dim · configurable · 200M tokens free | $0.06 | $3.00 | $1.05 | $16 |
| Voyage AI | voyage-3 1024 dim | $0.06 | $3.00 | $1.05 | $16 |
| Cohere | embed-english-v3.0 1024 dim | $0.10 | $5.00 | $1.75 | $26 |
| Cohere | embed-multilingual-v3.0 1024 dim | $0.10 | $5.00 | $1.75 | $26 |
| Cohere | embed-english-light-v3.0 384 dim · Smaller, cheaper at inference | $0.10 | $5.00 | $1.75 | $26 |
| Mistral | mistral-embed 1024 dim | $0.10 | $5.00 | $1.75 | $26 |
| Voyage AI | voyage-4-large 1024 dim · configurable · Top MTEB 2026; 200M tokens free | $0.12 | $6.00 | $2.10 | $31 |
| OpenAI | text-embedding-3-large 3072 dim · configurable · Matryoshka — truncate to 256/512/1024 without retrain | $0.13 | $6.50 | $2.28 | $34 |
| Gemini Embedding 3072 dim · configurable · Text-only | $0.15 | $7.50 | $2.63 | $39 | |
| Voyage AI | voyage-3-large 1024 dim · configurable · Legacy v3; consider voyage-4-large | $0.18 | $9.00 | $3.15 | $47 |
| Voyage AI | voyage-code-3 1024 dim · Optimized for code retrieval | $0.18 | $9.00 | $3.15 | $47 |
| Gemini Embedding 2 3072 dim · configurable · Multimodal: text $0.20, image $0.45, audio $6.50, video $12 per 1M tokens | $0.20 | $10.00 | $3.50 | $52 |
Frecuencia 0.25 significa re-embed el corpus cada 4 meses. Los modelos "configurable" soportan truncamiento Matryoshka — puedes reducir dimensiones después sin re-embedding.
Qué hace esta calculadora
9 proveedores comparados
OpenAI 3-small/large, Cohere v4, Voyage 3, Jina, Mistral, Google, Azure, BGE-M3 self-host.
One-time + recurring
Coste embed inicial + coste re-embed mensual separados.
Slider refresh frequency
Modela cuán a menudo re-embeddear (nunca, trimestral, mensual, semanal).
Break-even self-host
Compara managed APIs con BGE-M3 en H100 alquilado. Break-even ~2B tokens/mes.
Truncamiento dimension
Modelos Matryoshka (OpenAI 3-large) permiten truncar dimensions.
Modelado query tokens
Coste embedding es simétrico — query tokens también cuentan.
Comparación rápida
Coste embed corpus 500M tokens + 50M query tokens/mes
| Proveedor | One-time | Mensual | $/1M tokens |
|---|---|---|---|
| Jina v3 | $9 | $0.90 | $0.018 |
| Voyage 3 Lite | $10 | $1 | $0.02 |
| OpenAI text-embed-3-small | $10 | $1 | $0.02 |
| Cohere Embed v4 Light | $50 | $5 | $0.10 |
| Voyage 3 Large | $65 | $6.50 | $0.13 |
| OpenAI text-embed-3-large | $65 | $6.50 | $0.13 |
| Self-host BGE-M3 (H100) | ~$45 | ~$1,300 | flat /mes |
Self-host gana sobre ~2B tokens/mes total throughput.
Cómo usar esta calculadora
Calcula embed corpus one-time + re-embed recurring en 9 proveedores.
- 1
Entra tamaño corpus
Tokens en corpus completo. Documentos × tokens/doc. Típico: 1 doc = 500 tokens.
- 2
Set refresh frequency
0 = nunca, 1 = mensual, 4 = semanal. Mayoría corpus producción re-embed trimestral.
- 3
Añade query volume
Query tokens mensuales. A menudo el item más grande over time.
- 4
Compara y elige
Sort por coste mensual. Self-host BGE-M3 gana >2B tokens/mes.
Por qué usar esta calculadora
- ✓9 proveedores refrescados mensualmente
- ✓One-time + recurring split
- ✓Break-even self-host modelado
- ✓Matryoshka dimension truncation
- ✓Query tokens incluidos
- ✓Sin login